import torch
import torch.nn as nn
__all__ = ['MLLAttention', 'C2PSAMLLA']
class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)
    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x
class ConvLayer(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, padding=0, dilation=1, groups=1,
                 bias=True, dropout=0, norm=nn.BatchNorm2d, act_func=nn.ReLU):
        super(ConvLayer, self).__init__()
        self.dropout = nn.Dropout2d(dropout, inplace=False) if dropout > 0 else None
        self.conv = nn.Conv2d(
            in_channels,
            out_channels,
            kernel_size=(kernel_size, kernel_size),
            stride=(stride, stride),
            padding=(padding, padding),
            dilation=(dilation, dilation),
            groups=groups,
            bias=bias,
        )
        self.norm = norm(num_features=out_channels) if norm else None
        self.act = act_func() if act_func else None
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        if self.dropout is not None:
            x = self.dropout(x)
        x = self.conv(x)
        if self.norm:
            x = self.norm(x)
        if self.act:
            x = self.act(x)
        return x
class RoPE(torch.nn.Module):
    r"""Rotary Positional Embedding.
    """
    def __init__(self, base=10000):
        super(RoPE, self).__init__()
        self.base = base
    def generate_rotations(self, x):
        # 获取输入张量的形状
        *channel_dims, feature_dim = x.shape[1:-1][0], x.shape[-1]
        k_max = feature_dim // (2 * len(channel_dims))
        assert feature_dim % k_max == 0, "Feature dimension must be divisible by 2 * k_max"
        # 生成角度
        theta_ks = 1 / (self.base ** (torch.arange(k_max, dtype=x.dtype, device=x.device) / k_max))
        angles = torch.cat([t.unsqueeze(-1) * theta_ks for t in
                            torch.meshgrid([torch.arange(d, dtype=x.dtype, device=x.device) for d in channel_dims],
                                           indexing='ij')], dim=-1)
        # 计算旋转矩阵的实部和虚部
        rotations_re = torch.cos(angles).unsqueeze(dim=-1)
        rotations_im = torch.sin(angles).unsqueeze(dim=-1)
        rotations = torch.cat([rotations_re, rotations_im], dim=-1)
        return rotations
    def forward(self, x):
        # 生成旋转矩阵
        rotations = self.generate_rotations(x)
        # 将 x 转换为复数形式
        x_complex = torch.view_as_complex(x.reshape(*x.shape[:-1], -1, 2))
        # 应用旋转矩阵
        pe_x = torch.view_as_complex(rotations) * x_complex
        # 将结果转换回实数形式并展平最后两个维度
        return torch.view_as_real(pe_x).flatten(-2)
class MLLAttention(nn.Module):
    r""" Linear Attention with LePE and RoPE.
    Args:
        dim (int): Number of input channels.
        num_heads (int): Number of attention heads.
        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
    """
    def __init__(self, dim=3, input_resolution=[160, 160], num_heads=4, qkv_bias=True, **kwargs):
        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.num_heads = num_heads
        self.qk = nn.Linear(dim, dim * 2, bias=qkv_bias)
        self.elu = nn.ELU()
        self.lepe = nn.Conv2d(dim, dim, 3, padding=1, groups=dim)
        self.rope = RoPE()
    def forward(self, x):
        """
        Args:
            x: input features with shape of (B, N, C)
        """
        x = x.reshape((x.size(0), x.size(2) * x.size(3), x.size(1)))
        b, n, c = x.shape
        h = int(n ** 0.5)
        w = int(n ** 0.5)
        # self.rope = RoPE(shape=(h, w, self.dim))
        num_heads = self.num_heads
        head_dim = c // num_heads
        qk = self.qk(x).reshape(b, n, 2, c).permute(2, 0, 1, 3)
        q, k, v = qk[0], qk[1], x
        # q, k, v: b, n, c
        q = self.elu(q) + 1.0
        k = self.elu(k) + 1.0
        q_rope = self.rope(q.reshape(b, h, w, c)).reshape(b, n, num_heads, head_dim).permute(0, 2, 1, 3)
        k_rope = self.rope(k.reshape(b, h, w, c)).reshape(b, n, num_heads, head_dim).permute(0, 2, 1, 3)
        q = q.reshape(b, n, num_heads, head_dim).permute(0, 2, 1, 3)
        k = k.reshape(b, n, num_heads, head_dim).permute(0, 2, 1, 3)
        v = v.reshape(b, n, num_heads, head_dim).permute(0, 2, 1, 3)
        z = 1 / (q @ k.mean(dim=-2, keepdim=True).transpose(-2, -1) + 1e-6)
        kv = (k_rope.transpose(-2, -1) * (n ** -0.5)) @ (v * (n ** -0.5))
        x = q_rope @ kv * z
        x = x.transpose(1, 2).reshape(b, n, c)
        v = v.transpose(1, 2).reshape(b, h, w, c).permute(0, 3, 1, 2)
        x = x + self.lepe(v).permute(0, 2, 3, 1).reshape(b, n, c)
        x = x.transpose(2, 1).reshape((b, c, h, w))
        return x
    def extra_repr(self) -> str:
        return f'dim={self.dim}, num_heads={self.num_heads}'
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p
class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = nn.SiLU()  # default activation
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))
    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
class PSABlock(nn.Module):
    """
    PSABlock class implementing a Position-Sensitive Attention block for neural networks.
    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.
    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.
    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.
    Examples:
        Create a PSABlock and perform a forward pass
    """
    def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
        """Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction."""
        super().__init__()
        self.attn = MLLAttention(c)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut
    def forward(self, x):
        """Executes a forward pass through PSABlock, applying attention and feed-forward layers to the input tensor."""
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x
class C2PSAMLLA(nn.Module):
    """
    C2PSA module with attention mechanism for enhanced feature extraction and processing.
    This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
    capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.
    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
        m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.
    Methods:
        forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.
    Notes:
        This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.
    """
    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)
        self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))
    def forward(self, x):
        """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))

​

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSAMLLA, [1024]] # 10
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
  - [-1, 1, MLLAttention, []] # 17 (P3/8-small)  小目标检测层输出位置增加注意力机制
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 20 (P4/16-medium)
  - [-1, 1, MLLAttention, []] # 21 (P4/16-medium) 中目标检测层输出位置增加注意力机制
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 24 (P5/32-large)
  - [-1, 1, MLLAttention, []] # 25 (P5/32-large) 大目标检测层输出位置增加注意力机制
  # 注意力机制我这里其实是添加了三个但是实际一般生效就只添加一个就可以了，所以大家可以自行注释来尝试, 上面三个仅建议大家保留一个， 但是from位置要对齐.
  # 具体在那一层用注意力机制可以根据自己的数据集场景进行选择。
  # 如果你自己配置注意力位置注意from[17, 21, 25]位置要对应上对应的检测层！
  - [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
    model = YOLO('yolov8-MLLA.yaml')
    # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s,
    # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！
    # model.load('yolov8n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
    model.train(data=r"C:\Users\Administrator\PycharmProjects\yolov5-master\yolov5-master\Construction Site Safety.v30-raw-images_latestversion.yolov8\data.yaml",
                # 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
                cache=False,
                imgsz=640,
                epochs=150,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=0,
                workers=0,
                device='0',
                optimizer='SGD', # using SGD
                # resume='runs/train/exp21/weights/last.pt', # 如过想续训就设置last.pt的地址
                amp=True,  # 如果出现训练损失为Nan可以关闭amp
                project='runs/train',
                name='exp',
                )